diff --git a/README.md b/README.md
index 0eeb774..9be6f60 100644
--- a/README.md
+++ b/README.md
@@ -100,25 +100,31 @@ We recommend to use [ClickHouse local](https://clickhouse.com/docs/en/operations
 # count rows
 $ clickhouse local -q "SELECT count(*) FROM 'transactions.parquet' LIMIT 1;"
 
-# get the first hash+rawTx
+# show hash+rawTx from first entry
 $ clickhouse local -q "SELECT hash,hex(rawTx) FROM 'transactions.parquet' LIMIT 1;"
 
-# get details of a particular hash
+# details of a particular hash
 $ clickhouse local -q "SELECT timestamp,hash,from,to,hex(rawTx) FROM 'transactions.parquet' WHERE hash='0x152065ad73bcf63f68572f478e2dc6e826f1f434cb488b993e5956e6b7425eed';"
 
-# get exclusive transactions from bloxroute
+# all transactions seen from mempoolguru
+$ clickhouse local -q "SELECT COUNT(*) FROM 'transactions.parquet' WHERE has(sources, 'mempoolguru');"
+
+# all transactions that were seen by both mempoolguru and chainbound
+$ clickhouse local -q "SELECT COUNT(*) FROM 'transactions.parquet' WHERE hasAll(sources, ['mempoolguru', 'local']);"
+
+# exclusive transactions from bloxroute
 $ clickhouse local -q "SELECT COUNT(*) FROM 'transactions.parquet' WHERE length(sources) == 1 AND sources[1] == 'bloxroute';"
 
-# get count of landed vs not-landed exclusive transactions, by source
+# count of landed vs not-landed exclusive transactions, by source
 $ clickhouse local -q "WITH includedBlockTimestamp!=0 as included SELECT sources[1], included, count(included) FROM 'out/out/transactions.parquet' WHERE length(sources) == 1 GROUP BY sources[1], included;"
 
-# get uniswap v2 transactions
+# uniswap v2 transactions
 $ clickhouse local -q "SELECT COUNT(*) FROM 'transactions.parquet' WHERE to='0x7a250d5630b4cf539739df2c5dacb4c659f2488d';"
 
-# get uniswap v2 transactions and separate by included/not-included
+# uniswap v2 transactions and separate by included/not-included
 $ clickhouse local -q "WITH includedBlockTimestamp!=0 as included SELECT included, COUNT(included) FROM 'transactions.parquet' WHERE to='0x7a250d5630b4cf539739df2c5dacb4c659f2488d' GROUP BY included;"
 
-# get inclusion delay for uniswap v2 transactions (time between receiving and being included on-chain)
+# inclusion delay for uniswap v2 transactions (time between receiving and being included on-chain)
 $ clickhouse local -q "WITH inclusionDelayMs/1000 as incdelay SELECT quantiles(0.5, 0.9, 0.99)(incdelay), avg(incdelay) as avg FROM 'transactions.parquet' WHERE to='0x7a250d5630b4cf539739df2c5dacb4c659f2488d' AND includedBlockTimestamp!=0;"
 
 # count uniswap v2 contract methods
diff --git a/scripts/README.md b/scripts/README.md
index 48b3905..77abfc2 100644
--- a/scripts/README.md
+++ b/scripts/README.md
@@ -35,6 +35,9 @@ journalctl -u mempool-collector -o cat --since "10m ago" | grep "source_stats_al
 
 # source stats - tx first
 journalctl -u mempool-collector -o cat --since "1h ago" | grep "source_stats_first" | awk '{ $1=""; $2=""; $3=""; print $0}' | jq
+
+# count types of traash
+cat trash/*.csv | sed 's/,/ /g' | awk '{ print $4 }' | sort | uniq -c
 ```
 
 CSV tricks
diff --git a/scripts/upload.sh b/scripts/upload.sh
index d6b642e..237cc35 100755
--- a/scripts/upload.sh
+++ b/scripts/upload.sh
@@ -74,6 +74,10 @@ zip "${date}.csv.zip" "${date}.csv"
 gzip -k "${date}.csv"
 zip "${date}_sourcelog.csv.zip" "${date}_sourcelog.csv"
 
+# combine and zip trash files
+cat trash/*.csv > "${date}_trash.csv"
+zip "${date}_trash.csv.zip" "${date}_trash.csv"
+
 # upload to Cloudflare R2 and AWS S3
 echo "Uploading ${date}.parquet ..."
 aws s3 cp --no-progress "${date}.parquet" "s3://flashbots-mempool-dumpster/ethereum/mainnet/${ym}/" --endpoint-url "https://${CLOUDFLARE_R2_ACCOUNT_ID}.r2.cloudflarestorage.com"
@@ -94,22 +98,6 @@ echo "Uploading ${date}_sourcelog.csv.zip ..."
 aws s3 cp --no-progress "${date}_sourcelog.csv.zip" "s3://flashbots-mempool-dumpster/ethereum/mainnet/${ym}/" --endpoint-url "https://${CLOUDFLARE_R2_ACCOUNT_ID}.r2.cloudflarestorage.com"
 aws --profile aws s3 cp --no-progress "${date}_sourcelog.csv.zip" "s3://flashbots-mempool-dumpster/ethereum/mainnet/${ym}/"
 
-#
-# # Create analysis
-# #
-# echo "Creating summary..."
-# cd $1
-# /server/mempool-dumpster/build/analyze \
-#   --out "${date}_summary.txt" \
-#   --input-parquet "${date}.parquet" \
-#   --input-sourcelog "${date}_sourcelog.csv.zip"
-
-# /server/mempool-dumpster/build/analyze test \
-#   --tx-blacklist "../${yesterday}/${yesterday}.csv.zip" \
-#   --tx-whitelist "${date}.csv.zip" \
-#   --out "${date}_summary.txt" \
-#   "${date}_sourcelog.csv"
-
 echo "Uploading ${date}_summary.txt ..."
 aws s3 cp --no-progress "${date}_summary.txt" "s3://flashbots-mempool-dumpster/ethereum/mainnet/${ym}/" --endpoint-url "https://${CLOUDFLARE_R2_ACCOUNT_ID}.r2.cloudflarestorage.com"
 aws --profile aws s3 cp --no-progress "${date}_summary.txt" "s3://flashbots-mempool-dumpster/ethereum/mainnet/${ym}/"
@@ -118,7 +106,7 @@ aws --profile aws s3 cp --no-progress "${date}_summary.txt" "s3://flashbots-memp
 # CLEANUP
 #
 if [ -z ${YES:-} ]; then
-  read -p "Upload successful. Remove the raw transactions directory? " -n 1 -r
+  read -p "Upload successful. Remove the raw files and directories? " -n 1 -r
   echo
   if [[ ! $REPLY =~ ^[Yy]$ ]]
   then
@@ -126,7 +114,7 @@ if [ -z ${YES:-} ]; then
   fi
 fi
 
-rm -rf transactions sourcelog
-rm -rf "${date}_transactions.csv" "${date}.csv" "${date}_sourcelog.csv"
+rm -rf "${date}_transactions.csv" "${date}.csv" "${date}_sourcelog.csv" "${date}_trash.csv"
+rm -rf transactions sourcelog trash
 echo "All done!"
 echo ""